1M param OCR model - runs on CPU, 15x faster than tesseract, close to 1B+ param models in accuracy
Repository Index
47,133 repositories indexed
1–2 of 2 · Most stars
Local inference for diffusion language models (LLaDA, Dream), written in Mojo
47,133 repositories indexed
1–2 of 2 · Most stars
1M param OCR model - runs on CPU, 15x faster than tesseract, close to 1B+ param models in accuracy
Local inference for diffusion language models (LLaDA, Dream), written in Mojo